1 files changed, 322 insertions, 75 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index bd62712848f..93316a96d82 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -59,6 +59,11 @@ int sysctl_tcp_base_mss __read_mostly = 512;
 /* By default, RFC2861 behavior.  */
 int sysctl_tcp_slow_start_after_idle __read_mostly = 1;
 
+int sysctl_tcp_cookie_size __read_mostly = 0; /* TCP_COOKIE_MAX */
+EXPORT_SYMBOL_GPL(sysctl_tcp_cookie_size);
+
+
+/* Account for new data that has been sent to the network. */
 static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -142,6 +147,7 @@ static void tcp_cwnd_restart(struct sock *sk, struct dst_entry *dst)
 	tp->snd_cwnd_used = 0;
 }
 
+/* Congestion state accounting after a packet has been sent. */
 static void tcp_event_data_sent(struct tcp_sock *tp,
 				struct sk_buff *skb, struct sock *sk)
 {
@@ -161,6 +167,7 @@ static void tcp_event_data_sent(struct tcp_sock *tp,
 		icsk->icsk_ack.pingpong = 1;
 }
 
+/* Account for an ACK we sent. */
 static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts)
 {
 	tcp_dec_quickack_mode(sk, pkts);
@@ -276,6 +283,7 @@ static u16 tcp_select_window(struct sock *sk)
 	return new_win;
 }
 
+/* Packet ECN state for a SYN-ACK */
 static inline void TCP_ECN_send_synack(struct tcp_sock *tp, struct sk_buff *skb)
 {
 	TCP_SKB_CB(skb)->flags &= ~TCPCB_FLAG_CWR;
@@ -283,6 +291,7 @@ static inline void TCP_ECN_send_synack(struct tcp_sock *tp, struct sk_buff *skb)
 		TCP_SKB_CB(skb)->flags &= ~TCPCB_FLAG_ECE;
 }
 
+/* Packet ECN state for a SYN.  */
 static inline void TCP_ECN_send_syn(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -301,6 +310,9 @@ TCP_ECN_make_synack(struct request_sock *req, struct tcphdr *th)
 		th->ece = 1;
 }
 
+/* Set up ECN state for a packet on a ESTABLISHED socket that is about to
+ * be sent.
+ */
 static inline void TCP_ECN_send(struct sock *sk, struct sk_buff *skb,
 				int tcp_header_len)
 {
@@ -353,16 +365,49 @@ static inline int tcp_urg_mode(const struct tcp_sock *tp)
 #define OPTION_SACK_ADVERTISE	(1 << 0)
 #define OPTION_TS		(1 << 1)
 #define OPTION_MD5		(1 << 2)
+#define OPTION_WSCALE		(1 << 3)
+#define OPTION_COOKIE_EXTENSION	(1 << 4)
 
 struct tcp_out_options {
 	u8 options;		/* bit field of OPTION_* */
 	u8 ws;			/* window scale, 0 to disable */
 	u8 num_sack_blocks;	/* number of SACK blocks to include */
+	u8 hash_size;		/* bytes in hash_location */
 	u16 mss;		/* 0 to disable */
 	__u32 tsval, tsecr;	/* need to include OPTION_TS */
+	__u8 *hash_location;	/* temporary pointer, overloaded */
 };
 
-/* Beware: Something in the Internet is very sensitive to the ordering of
+/* The sysctl int routines are generic, so check consistency here.
+ */
+static u8 tcp_cookie_size_check(u8 desired)
+{
+	if (desired > 0) {
+		/* previously specified */
+		return desired;
+	}
+	if (sysctl_tcp_cookie_size <= 0) {
+		/* no default specified */
+		return 0;
+	}
+	if (sysctl_tcp_cookie_size <= TCP_COOKIE_MIN) {
+		/* value too small, specify minimum */
+		return TCP_COOKIE_MIN;
+	}
+	if (sysctl_tcp_cookie_size >= TCP_COOKIE_MAX) {
+		/* value too large, specify maximum */
+		return TCP_COOKIE_MAX;
+	}
+	if (0x1 & sysctl_tcp_cookie_size) {
+		/* 8-bit multiple, illegal, fix it */
+		return (u8)(sysctl_tcp_cookie_size + 0x1);
+	}
+	return (u8)sysctl_tcp_cookie_size;
+}
+
+/* Write previously computed TCP options to the packet.
+ *
+ * Beware: Something in the Internet is very sensitive to the ordering of
  * TCP options, we learned this through the hard way, so be careful here.
  * Luckily we can at least blame others for their non-compliance but from
  * inter-operatibility perspective it seems that we're somewhat stuck with
@@ -374,17 +419,34 @@ struct tcp_out_options {
  * (but it may well be that other scenarios fail similarly).
  */
 static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
-			      const struct tcp_out_options *opts,
-			      __u8 **md5_hash) {
-	if (unlikely(OPTION_MD5 & opts->options)) {
-		*ptr++ = htonl((TCPOPT_NOP << 24) |
-			       (TCPOPT_NOP << 16) |
-			       (TCPOPT_MD5SIG << 8) |
-			       TCPOLEN_MD5SIG);
-		*md5_hash = (__u8 *)ptr;
+			      struct tcp_out_options *opts)
+{
+	u8 options = opts->options;	/* mungable copy */
+
+	/* Having both authentication and cookies for security is redundant,
+	 * and there's certainly not enough room.  Instead, the cookie-less
+	 * extension variant is proposed.
+	 *
+	 * Consider the pessimal case with authentication.  The options
+	 * could look like:
+	 *   COOKIE|MD5(20) + MSS(4) + SACK|TS(12) + WSCALE(4) == 40
+	 */
+	if (unlikely(OPTION_MD5 & options)) {
+		if (unlikely(OPTION_COOKIE_EXTENSION & options)) {
+			*ptr++ = htonl((TCPOPT_COOKIE << 24) |
+				       (TCPOLEN_COOKIE_BASE << 16) |
+				       (TCPOPT_MD5SIG << 8) |
+				       TCPOLEN_MD5SIG);
+		} else {
+			*ptr++ = htonl((TCPOPT_NOP << 24) |
+				       (TCPOPT_NOP << 16) |
+				       (TCPOPT_MD5SIG << 8) |
+				       TCPOLEN_MD5SIG);
+		}
+		options &= ~OPTION_COOKIE_EXTENSION;
+		/* overload cookie hash location */
+		opts->hash_location = (__u8 *)ptr;
 		ptr += 4;
-	} else {
-		*md5_hash = NULL;
 	}
 
 	if (unlikely(opts->mss)) {
@@ -393,12 +455,13 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
 			       opts->mss);
 	}
 
-	if (likely(OPTION_TS & opts->options)) {
-		if (unlikely(OPTION_SACK_ADVERTISE & opts->options)) {
+	if (likely(OPTION_TS & options)) {
+		if (unlikely(OPTION_SACK_ADVERTISE & options)) {
 			*ptr++ = htonl((TCPOPT_SACK_PERM << 24) |
 				       (TCPOLEN_SACK_PERM << 16) |
 				       (TCPOPT_TIMESTAMP << 8) |
 				       TCPOLEN_TIMESTAMP);
+			options &= ~OPTION_SACK_ADVERTISE;
 		} else {
 			*ptr++ = htonl((TCPOPT_NOP << 24) |
 				       (TCPOPT_NOP << 16) |
@@ -409,15 +472,52 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
 		*ptr++ = htonl(opts->tsecr);
 	}
 
-	if (unlikely(OPTION_SACK_ADVERTISE & opts->options &&
-		     !(OPTION_TS & opts->options))) {
+	/* Specification requires after timestamp, so do it now.
+	 *
+	 * Consider the pessimal case without authentication.  The options
+	 * could look like:
+	 *   MSS(4) + SACK|TS(12) + COOKIE(20) + WSCALE(4) == 40
+	 */
+	if (unlikely(OPTION_COOKIE_EXTENSION & options)) {
+		__u8 *cookie_copy = opts->hash_location;
+		u8 cookie_size = opts->hash_size;
+
+		/* 8-bit multiple handled in tcp_cookie_size_check() above,
+		 * and elsewhere.
+		 */
+		if (0x2 & cookie_size) {
+			__u8 *p = (__u8 *)ptr;
+
+			/* 16-bit multiple */
+			*p++ = TCPOPT_COOKIE;
+			*p++ = TCPOLEN_COOKIE_BASE + cookie_size;
+			*p++ = *cookie_copy++;
+			*p++ = *cookie_copy++;
+			ptr++;
+			cookie_size -= 2;
+		} else {
+			/* 32-bit multiple */
+			*ptr++ = htonl(((TCPOPT_NOP << 24) |
+					(TCPOPT_NOP << 16) |
+					(TCPOPT_COOKIE << 8) |
+					TCPOLEN_COOKIE_BASE) +
+				       cookie_size);
+		}
+
+		if (cookie_size > 0) {
+			memcpy(ptr, cookie_copy, cookie_size);
+			ptr += (cookie_size / 4);
+		}
+	}
+
+	if (unlikely(OPTION_SACK_ADVERTISE & options)) {
 		*ptr++ = htonl((TCPOPT_NOP << 24) |
 			       (TCPOPT_NOP << 16) |
 			       (TCPOPT_SACK_PERM << 8) |
 			       TCPOLEN_SACK_PERM);
 	}
 
-	if (unlikely(opts->ws)) {
+	if (unlikely(OPTION_WSCALE & options)) {
 		*ptr++ = htonl((TCPOPT_NOP << 24) |
 			       (TCPOPT_WINDOW << 16) |
 			       (TCPOLEN_WINDOW << 8) |
@@ -445,17 +545,25 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
 	}
 }
 
+/* Compute TCP options for SYN packets. This is not the final
+ * network wire format yet.
+ */
 static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 				struct tcp_out_options *opts,
 				struct tcp_md5sig_key **md5) {
 	struct tcp_sock *tp = tcp_sk(sk);
-	unsigned size = 0;
+	struct tcp_cookie_values *cvp = tp->cookie_values;
+	struct dst_entry *dst = __sk_dst_get(sk);
+	unsigned remaining = MAX_TCP_OPTION_SPACE;
+	u8 cookie_size = (!tp->rx_opt.cookie_out_never && cvp != NULL) ?
+			 tcp_cookie_size_check(cvp->cookie_desired) :
+			 0;
 
 #ifdef CONFIG_TCP_MD5SIG
 	*md5 = tp->af_specific->md5_lookup(sk, sk);
 	if (*md5) {
 		opts->options |= OPTION_MD5;
-		size += TCPOLEN_MD5SIG_ALIGNED;
+		remaining -= TCPOLEN_MD5SIG_ALIGNED;
 	}
 #else
 	*md5 = NULL;
@@ -471,76 +579,159 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 	 * SACKs don't matter, we never delay an ACK when we have any of those
 	 * going out.  */
 	opts->mss = tcp_advertise_mss(sk);
-	size += TCPOLEN_MSS_ALIGNED;
+	remaining -= TCPOLEN_MSS_ALIGNED;
 
-	if (likely(sysctl_tcp_timestamps && *md5 == NULL)) {
+	if (likely(sysctl_tcp_timestamps &&
+		   !dst_feature(dst, RTAX_FEATURE_NO_TSTAMP) &&
+		   *md5 == NULL)) {
 		opts->options |= OPTION_TS;
 		opts->tsval = TCP_SKB_CB(skb)->when;
 		opts->tsecr = tp->rx_opt.ts_recent;
-		size += TCPOLEN_TSTAMP_ALIGNED;
+		remaining -= TCPOLEN_TSTAMP_ALIGNED;
 	}
-	if (likely(sysctl_tcp_window_scaling)) {
+	if (likely(sysctl_tcp_window_scaling &&
+		   !dst_feature(dst, RTAX_FEATURE_NO_WSCALE))) {
 		opts->ws = tp->rx_opt.rcv_wscale;
-		if (likely(opts->ws))
-			size += TCPOLEN_WSCALE_ALIGNED;
+		opts->options |= OPTION_WSCALE;
+		remaining -= TCPOLEN_WSCALE_ALIGNED;
 	}
-	if (likely(sysctl_tcp_sack)) {
+	if (likely(sysctl_tcp_sack &&
+		   !dst_feature(dst, RTAX_FEATURE_NO_SACK))) {
 		opts->options |= OPTION_SACK_ADVERTISE;
 		if (unlikely(!(OPTION_TS & opts->options)))
-			size += TCPOLEN_SACKPERM_ALIGNED;
+			remaining -= TCPOLEN_SACKPERM_ALIGNED;
 	}
 
-	return size;
+	/* Note that timestamps are required by the specification.
+	 *
+	 * Odd numbers of bytes are prohibited by the specification, ensuring
+	 * that the cookie is 16-bit aligned, and the resulting cookie pair is
+	 * 32-bit aligned.
+	 */
+	if (*md5 == NULL &&
+	    (OPTION_TS & opts->options) &&
+	    cookie_size > 0) {
+		int need = TCPOLEN_COOKIE_BASE + cookie_size;
+
+		if (0x2 & need) {
+			/* 32-bit multiple */
+			need += 2; /* NOPs */
+
+			if (need > remaining) {
+				/* try shrinking cookie to fit */
+				cookie_size -= 2;
+				need -= 4;
+			}
+		}
+		while (need > remaining && TCP_COOKIE_MIN <= cookie_size) {
+			cookie_size -= 4;
+			need -= 4;
+		}
+		if (TCP_COOKIE_MIN <= cookie_size) {
+			opts->options |= OPTION_COOKIE_EXTENSION;
+			opts->hash_location = (__u8 *)&cvp->cookie_pair[0];
+			opts->hash_size = cookie_size;
+
+			/* Remember for future incarnations. */
+			cvp->cookie_desired = cookie_size;
+
+			if (cvp->cookie_desired != cvp->cookie_pair_size) {
+				/* Currently use random bytes as a nonce,
+				 * assuming these are completely unpredictable
+				 * by hostile users of the same system.
+				 */
+				get_random_bytes(&cvp->cookie_pair[0],
+						 cookie_size);
+				cvp->cookie_pair_size = cookie_size;
+			}
+
+			remaining -= need;
+		}
+	}
+	return MAX_TCP_OPTION_SPACE - remaining;
 }
 
+/* Set up TCP options for SYN-ACKs. */
 static unsigned tcp_synack_options(struct sock *sk,
 				   struct request_sock *req,
 				   unsigned mss, struct sk_buff *skb,
 				   struct tcp_out_options *opts,
-				   struct tcp_md5sig_key **md5) {
-	unsigned size = 0;
+				   struct tcp_md5sig_key **md5,
+				   struct tcp_extend_values *xvp)
+{
 	struct inet_request_sock *ireq = inet_rsk(req);
-	char doing_ts;
+	unsigned remaining = MAX_TCP_OPTION_SPACE;
+	u8 cookie_plus = (xvp != NULL && !xvp->cookie_out_never) ?
+			 xvp->cookie_plus :
+			 0;
+	bool doing_ts = ireq->tstamp_ok;
 
 #ifdef CONFIG_TCP_MD5SIG
 	*md5 = tcp_rsk(req)->af_specific->md5_lookup(sk, req);
 	if (*md5) {
 		opts->options |= OPTION_MD5;
-		size += TCPOLEN_MD5SIG_ALIGNED;
+		remaining -= TCPOLEN_MD5SIG_ALIGNED;
+
+		/* We can't fit any SACK blocks in a packet with MD5 + TS
+		 * options. There was discussion about disabling SACK
+		 * rather than TS in order to fit in better with old,
+		 * buggy kernels, but that was deemed to be unnecessary.
+		 */
+		doing_ts &= !ireq->sack_ok;
 	}
 #else
 	*md5 = NULL;
 #endif
 
-	/* we can't fit any SACK blocks in a packet with MD5 + TS
-	   options. There was discussion about disabling SACK rather than TS in
-	   order to fit in better with old, buggy kernels, but that was deemed
-	   to be unnecessary. */
-	doing_ts = ireq->tstamp_ok && !(*md5 && ireq->sack_ok);
-
+	/* We always send an MSS option. */
 	opts->mss = mss;
-	size += TCPOLEN_MSS_ALIGNED;
+	remaining -= TCPOLEN_MSS_ALIGNED;
 
 	if (likely(ireq->wscale_ok)) {
 		opts->ws = ireq->rcv_wscale;
-		if (likely(opts->ws))
-			size += TCPOLEN_WSCALE_ALIGNED;
+		opts->options |= OPTION_WSCALE;
+		remaining -= TCPOLEN_WSCALE_ALIGNED;
 	}
 	if (likely(doing_ts)) {
 		opts->options |= OPTION_TS;
 		opts->tsval = TCP_SKB_CB(skb)->when;
 		opts->tsecr = req->ts_recent;
-		size += TCPOLEN_TSTAMP_ALIGNED;
+		remaining -= TCPOLEN_TSTAMP_ALIGNED;
 	}
 	if (likely(ireq->sack_ok)) {
 		opts->options |= OPTION_SACK_ADVERTISE;
 		if (unlikely(!doing_ts))
-			size += TCPOLEN_SACKPERM_ALIGNED;
+			remaining -= TCPOLEN_SACKPERM_ALIGNED;
 	}
 
-	return size;
+	/* Similar rationale to tcp_syn_options() applies here, too.
+	 * If the <SYN> options fit, the same options should fit now!
+	 */
+	if (*md5 == NULL &&
+	    doing_ts &&
+	    cookie_plus > TCPOLEN_COOKIE_BASE) {
+		int need = cookie_plus; /* has TCPOLEN_COOKIE_BASE */
+
+		if (0x2 & need) {
+			/* 32-bit multiple */
+			need += 2; /* NOPs */
+		}
+		if (need <= remaining) {
+			opts->options |= OPTION_COOKIE_EXTENSION;
+			opts->hash_size = cookie_plus - TCPOLEN_COOKIE_BASE;
+			remaining -= need;
+		} else {
+			/* There's no error return, so flag it. */
+			xvp->cookie_out_never = 1; /* true */
+			opts->hash_size = 0;
+		}
+	}
+	return MAX_TCP_OPTION_SPACE - remaining;
 }
 
+/* Compute TCP options for ESTABLISHED sockets. This is not the
+ * final wire format yet.
+ */
 static unsigned tcp_established_options(struct sock *sk, struct sk_buff *skb,
 					struct tcp_out_options *opts,
 					struct tcp_md5sig_key **md5) {
@@ -601,7 +792,6 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	struct tcp_out_options opts;
 	unsigned tcp_options_size, tcp_header_size;
 	struct tcp_md5sig_key *md5;
-	__u8 *md5_hash_location;
 	struct tcphdr *th;
 	int err;
 
@@ -643,8 +833,8 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 
 	/* Build TCP header and checksum it. */
 	th = tcp_hdr(skb);
-	th->source		= inet->sport;
-	th->dest		= inet->dport;
+	th->source		= inet->inet_sport;
+	th->dest		= inet->inet_dport;
 	th->seq			= htonl(tcb->seq);
 	th->ack_seq		= htonl(tp->rcv_nxt);
 	*(((__be16 *)th) + 6)	= htons(((tcp_header_size >> 2) << 12) |
@@ -672,7 +862,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 		}
 	}
 
-	tcp_options_write((__be32 *)(th + 1), tp, &opts, &md5_hash_location);
+	tcp_options_write((__be32 *)(th + 1), tp, &opts);
 	if (likely((tcb->flags & TCPCB_FLAG_SYN) == 0))
 		TCP_ECN_send(sk, skb, tcp_header_size);
 
@@ -680,7 +870,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	/* Calculate the MD5 hash, as we have all we need now */
 	if (md5) {
 		sk->sk_route_caps &= ~NETIF_F_GSO_MASK;
-		tp->af_specific->calc_md5_hash(md5_hash_location,
+		tp->af_specific->calc_md5_hash(opts.hash_location,
 					       md5, sk, NULL, skb);
 	}
 #endif
@@ -705,7 +895,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	return net_xmit_eval(err);
 }
 
-/* This routine just queue's the buffer
+/* This routine just queues the buffer for sending.
  *
  * NOTE: probe0 timer is not checked, do not forget tcp_push_pending_frames,
  * otherwise socket can stall.
@@ -722,6 +912,7 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb)
 	sk_mem_charge(sk, skb->truesize);
 }
 
+/* Initialize TSO segments for a packet. */
 static void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb,
 				 unsigned int mss_now)
 {
@@ -909,6 +1100,7 @@ static void __pskb_trim_head(struct sk_buff *skb, int len)
 	skb->len = skb->data_len;
 }
 
+/* Remove acked data from a packet in the transmit queue. */
 int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
 {
 	if (skb_cloned(skb) && pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
@@ -937,7 +1129,7 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
 	return 0;
 }
 
-/* Not accounting for SACKs here. */
+/* Calculate MSS. Not accounting for SACKs here.  */
 int tcp_mtu_to_mss(struct sock *sk, int pmtu)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -981,6 +1173,7 @@ int tcp_mss_to_mtu(struct sock *sk, int mss)
 	return mtu;
 }
 
+/* MTU probing init per socket */
 void tcp_mtup_init(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -1143,7 +1336,8 @@ static inline unsigned int tcp_cwnd_test(struct tcp_sock *tp,
 	return 0;
 }
 
-/* This must be invoked the first time we consider transmitting
+/* Intialize TSO state of a skb.
+ * This must be invoked the first time we consider transmitting
  * SKB onto the wire.
  */
 static int tcp_init_tso_segs(struct sock *sk, struct sk_buff *skb,
@@ -1158,6 +1352,7 @@ static int tcp_init_tso_segs(struct sock *sk, struct sk_buff *skb,
 	return tso_segs;
 }
 
+/* Minshall's variant of the Nagle send check. */
 static inline int tcp_minshall_check(const struct tcp_sock *tp)
 {
 	return after(tp->snd_sml, tp->snd_una) &&
@@ -1242,6 +1437,7 @@ static unsigned int tcp_snd_test(struct sock *sk, struct sk_buff *skb,
 	return cwnd_quota;
 }
 
+/* Test if sending is allowed right now. */
 int tcp_may_send_now(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -1378,6 +1574,10 @@ send_now:
 }
 
 /* Create a new MTU probe if we are ready.
+ * MTU probe is regularly attempting to increase the path MTU by
+ * deliberately sending larger packets.  This discovers routing
+ * changes resulting in larger path MTUs.
+ *
  * Returns 0 if we should wait to probe (no cwnd available),
  *         1 if a probe was sent,
  *         -1 otherwise
@@ -1790,6 +1990,7 @@ static void tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb)
 	sk_wmem_free_skb(sk, next_skb);
 }
 
+/* Check if coalescing SKBs is legal. */
 static int tcp_can_collapse(struct sock *sk, struct sk_buff *skb)
 {
 	if (tcp_skb_pcount(skb) > 1)
@@ -1808,6 +2009,9 @@ static int tcp_can_collapse(struct sock *sk, struct sk_buff *skb)
 	return 1;
 }
 
+/* Collapse packets in the retransmit queue to make to create
+ * less packets on the wire. This is only done on retransmission.
+ */
 static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to,
 				     int space)
 {
@@ -1886,8 +2090,8 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 	 * case, when window is shrunk to zero. In this case
 	 * our retransmit serves as a zero window probe.
 	 */
-	if (!before(TCP_SKB_CB(skb)->seq, tcp_wnd_end(tp))
-	    && TCP_SKB_CB(skb)->seq != tp->snd_una)
+	if (!before(TCP_SKB_CB(skb)->seq, tcp_wnd_end(tp)) &&
+	    TCP_SKB_CB(skb)->seq != tp->snd_una)
 		return -EAGAIN;
 
 	if (skb->len > cur_mss) {
@@ -1957,6 +2161,9 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 	return err;
 }
 
+/* Check if we forward retransmits are possible in the current
+ * window/congestion state.
+ */
 static int tcp_can_forward_retransmit(struct sock *sk)
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
@@ -2101,7 +2308,8 @@ void tcp_send_fin(struct sock *sk)
 	} else {
 		/* Socket is locked, keep trying until memory is available. */
 		for (;;) {
-			skb = alloc_skb_fclone(MAX_TCP_HEADER, GFP_KERNEL);
+			skb = alloc_skb_fclone(MAX_TCP_HEADER,
+					       sk->sk_allocation);
 			if (skb)
 				break;
 			yield();
@@ -2145,7 +2353,8 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority)
 	TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTRSTS);
 }
 
-/* WARNING: This routine must only be called when we have already sent
+/* Send a crossed SYN-ACK during socket establishment.
+ * WARNING: This routine must only be called when we have already sent
  * a SYN packet that crossed the incoming SYN that caused this routine
  * to get called. If this assumption fails then the initial rcv_wnd
  * and rcv_wscale values will not be correct.
@@ -2180,20 +2389,19 @@ int tcp_send_synack(struct sock *sk)
 	return tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
 }
 
-/*
- * Prepare a SYN-ACK.
- */
+/* Prepare a SYN-ACK. */
 struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
-				struct request_sock *req)
+				struct request_sock *req,
+				struct request_values *rvp)
 {
+	struct tcp_out_options opts;
+	struct tcp_extend_values *xvp = tcp_xv(rvp);
 	struct inet_request_sock *ireq = inet_rsk(req);
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcphdr *th;
-	int tcp_header_size;
-	struct tcp_out_options opts;
 	struct sk_buff *skb;
 	struct tcp_md5sig_key *md5;
-	__u8 *md5_hash_location;
+	int tcp_header_size;
 	int mss;
 
 	skb = sock_wmalloc(sk, MAX_TCP_HEADER + 15, 1, GFP_ATOMIC);
@@ -2231,8 +2439,8 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 #endif
 	TCP_SKB_CB(skb)->when = tcp_time_stamp;
 	tcp_header_size = tcp_synack_options(sk, req, mss,
-					     skb, &opts, &md5) +
-			  sizeof(struct tcphdr);
+					     skb, &opts, &md5, xvp)
+			+ sizeof(*th);
 
 	skb_push(skb, tcp_header_size);
 	skb_reset_transport_header(skb);
@@ -2249,19 +2457,58 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 	 */
 	tcp_init_nondata_skb(skb, tcp_rsk(req)->snt_isn,
 			     TCPCB_FLAG_SYN | TCPCB_FLAG_ACK);
+
+	if (OPTION_COOKIE_EXTENSION & opts.options) {
+		const struct tcp_cookie_values *cvp = tp->cookie_values;
+
+		if (cvp != NULL &&
+		    cvp->s_data_constant &&
+		    cvp->s_data_desired > 0) {
+			u8 *buf = skb_put(skb, cvp->s_data_desired);
+
+			/* copy data directly from the listening socket. */
+			memcpy(buf, cvp->s_data_payload, cvp->s_data_desired);
+			TCP_SKB_CB(skb)->end_seq += cvp->s_data_desired;
+		}
+
+		if (opts.hash_size > 0) {
+			__u32 workspace[SHA_WORKSPACE_WORDS];
+			u32 *mess = &xvp->cookie_bakery[COOKIE_DIGEST_WORDS];
+			u32 *tail = &mess[COOKIE_MESSAGE_WORDS-1];
+
+			/* Secret recipe depends on the Timestamp, (future)
+			 * Sequence and Acknowledgment Numbers, Initiator
+			 * Cookie, and others handled by IP variant caller.
+			 */
+			*tail-- ^= opts.tsval;
+			*tail-- ^= tcp_rsk(req)->rcv_isn + 1;
+			*tail-- ^= TCP_SKB_CB(skb)->seq + 1;
+
+			/* recommended */
+			*tail-- ^= ((th->dest << 16) | th->source);
+			*tail-- ^= (u32)(unsigned long)cvp; /* per sockopt */
+
+			sha_transform((__u32 *)&xvp->cookie_bakery[0],
+				      (char *)mess,
+				      &workspace[0]);
+			opts.hash_location =
+				(__u8 *)&xvp->cookie_bakery[0];
+		}
+	}
+
 	th->seq = htonl(TCP_SKB_CB(skb)->seq);
 	th->ack_seq = htonl(tcp_rsk(req)->rcv_isn + 1);
 
 	/* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */
 	th->window = htons(min(req->rcv_wnd, 65535U));
-	tcp_options_write((__be32 *)(th + 1), tp, &opts, &md5_hash_location);
+	tcp_options_write((__be32 *)(th + 1), tp, &opts);
 	th->doff = (tcp_header_size >> 2);
 	TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS);
 
 #ifdef CONFIG_TCP_MD5SIG
 	/* Okay, we have all we need - do the md5 hash if needed */
 	if (md5) {
-		tcp_rsk(req)->af_specific->calc_md5_hash(md5_hash_location,
+		tcp_rsk(req)->af_specific->calc_md5_hash(opts.hash_location,
 					       md5, NULL, req, skb);
 	}
 #endif
@@ -2269,9 +2516,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 	return skb;
 }
 
-/*
- * Do all connect socket setups that can be done AF independent.
- */
+/* Do all connect socket setups that can be done AF independent. */
 static void tcp_connect_init(struct sock *sk)
 {
 	struct dst_entry *dst = __sk_dst_get(sk);
@@ -2282,7 +2527,9 @@ static void tcp_connect_init(struct sock *sk)
 	 * See tcp_input.c:tcp_rcv_state_process case TCP_SYN_SENT.
 	 */
 	tp->tcp_header_len = sizeof(struct tcphdr) +
-		(sysctl_tcp_timestamps ? TCPOLEN_TSTAMP_ALIGNED : 0);
+		(sysctl_tcp_timestamps &&
+		(!dst_feature(dst, RTAX_FEATURE_NO_TSTAMP) ?
+		  TCPOLEN_TSTAMP_ALIGNED : 0));
 
 #ifdef CONFIG_TCP_MD5SIG
 	if (tp->af_specific->md5_lookup(sk, sk) != NULL)
@@ -2308,7 +2555,8 @@ static void tcp_connect_init(struct sock *sk)
 				  tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0),
 				  &tp->rcv_wnd,
 				  &tp->window_clamp,
-				  sysctl_tcp_window_scaling,
+				  (sysctl_tcp_window_scaling &&
+				   !dst_feature(dst, RTAX_FEATURE_NO_WSCALE)),
 				  &rcv_wscale);
 
 	tp->rx_opt.rcv_wscale = rcv_wscale;
@@ -2330,9 +2578,7 @@ static void tcp_connect_init(struct sock *sk)
 	tcp_clear_retrans(tp);
 }
 
-/*
- * Build a SYN and send it off.
- */
+/* Build a SYN and send it off. */
 int tcp_connect(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -2359,7 +2605,7 @@ int tcp_connect(struct sock *sk)
 	sk->sk_wmem_queued += buff->truesize;
 	sk_mem_charge(sk, buff->truesize);
 	tp->packets_out += tcp_skb_pcount(buff);
-	tcp_transmit_skb(sk, buff, 1, GFP_KERNEL);
+	tcp_transmit_skb(sk, buff, 1, sk->sk_allocation);
 
 	/* We change tp->snd_nxt after the tcp_transmit_skb() call
 	 * in order to make this packet get counted in tcpOutSegs.
@@ -2493,6 +2739,7 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent)
 	return tcp_transmit_skb(sk, skb, 0, GFP_ATOMIC);
 }
 
+/* Initiate keepalive or window probe from timer. */
 int tcp_write_wakeup(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);